© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14448
    Prev
    Next
    INDEX
    Explanations

    abbreviations of organizations, particularly governmental or industry groups

    oai_token-act-pair · gemini-2.0-flash

    verbs related to publishing and organizing activities

    np_token-act-pair-logits · gpt-4o-mini

    publishing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     strdup
    -0.50
     doty
    -0.49
     bleeding
    -0.48
    <_>
    -0.46
     dawn
    -0.46
    thea
    -0.42
    føl
    -0.42
    ///
    -0.41
     verba
    -0.41
    NamedQuery
    -0.41
    POSITIVE LOGITS
     publishes
    1.07
     published
    0.94
     launched
    0.93
     conducts
    0.90
     publicó
    0.89
     conducted
    0.88
     organizes
    0.88
     offers
    0.88
     hosts
    0.88
     publish
    0.86
    Activations Density 3.593%

    No Known Activations